Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A method of generating a media stream, the method comprising: iteratively adjusting media content included in a media stream based on evaluation of messages provided to a data management platform by a client device over time, wherein iteratively adjusting includes: receiving over time, at a data management platform, messages including indications that a user associated with a user client device has played out particular media items included in a media stream, the messages generated by the user client device in response to encountering contextual markers integrated within spot blocks adjacent to the particular media items in the media stream, the contextual markers including information related to advertisement content included in the spot blocks and to the particular media items; in response to receipt of the messages, recording, in a memory, an association between the user and the particular media items; identifying, by the data management platform, at least one audience segment associated with the particular media items; generating segment association information, the segment association information associating the user with the at least one audience segment, based, at least in part, on the association between the user and the particular media items and the association between the particular media items and the at least one audience segment; transmitting the segment association information from the data management platform to an advertisement server, the advertisement server configured to iteratively refine a targeting specificity of advertisement content provided to a streaming server by the advertising server; and generating, at the streaming server a media stream including spot blocks, the spot blocks including the advertisement content provided by the advertising server and the contextual markers.
This invention relates to dynamically adjusting media streams based on user engagement data to improve targeted advertising. The system involves a data management platform that receives messages from client devices when users interact with media content. These messages are triggered by contextual markers embedded in spot blocks adjacent to media items within the stream. The markers contain metadata about the advertisement content and the media items. Upon receiving these messages, the platform records associations between users and the media items they engage with. The platform then identifies audience segments linked to those media items and generates segment association information, which ties the user to the relevant audience segments. This information is sent to an advertisement server, which refines its targeting algorithms to deliver more personalized ads. The streaming server then generates an updated media stream with spot blocks containing the refined advertisement content and contextual markers. The iterative process allows the system to continuously adapt the media stream based on real-time user engagement data, enhancing the relevance of advertisements for individual users.
2. The method of claim 1 , further comprising: incrementing an instance counter describing a number of instances the user has been associated with the particular media item by a value of one; and associating the user with the audience segment if the instance counter meets a preset threshold value.
This invention relates to audience segmentation in media consumption tracking. The problem addressed is accurately identifying and categorizing users based on their repeated interactions with specific media items, such as songs, videos, or advertisements, to improve targeted content delivery or analytics. The method involves monitoring user interactions with a media item, such as playback or engagement events. When a user interacts with a media item, an instance counter is incremented by one, tracking the number of times the user has been associated with that media item. If the instance counter reaches a preset threshold value, the user is automatically assigned to a predefined audience segment. This segmentation allows for more precise targeting, personalized recommendations, or behavioral analysis. The method ensures that audience segmentation is based on measurable, repeated engagement rather than a single interaction, improving the reliability of user categorization. The preset threshold can be dynamically adjusted based on factors like media type, user demographics, or business objectives. This approach enhances the accuracy of audience segmentation systems by filtering out one-time or incidental interactions, focusing instead on users with consistent engagement patterns.
3. The method of claim 2 , further comprising: determining a recency associated with at least some of the instances the user has been associated with the particular media item; and associating the user with the audience segment if the instance counter meets the preset threshold value, and the recency of the at least some of the instances the user has been associated with the particular media item meets a preset threshold time indicator.
This invention relates to audience segmentation in media analytics, specifically improving the accuracy of user categorization by incorporating both frequency and recency of user interactions with media items. The problem addressed is the need to distinguish between users who have a genuine, ongoing interest in a media item versus those with sporadic or outdated engagement, ensuring more precise audience targeting. The method involves tracking instances where a user interacts with a particular media item, such as viewing, listening, or engaging with content. An instance counter tallies these interactions, and if the count meets a preset threshold, the user is initially considered for association with a specific audience segment. To refine this, the method further evaluates the recency of these interactions. If the most recent interactions fall within a preset time window (e.g., the last 30 days), the user is definitively assigned to the segment. This dual criteria—frequency and recency—ensures that only actively engaged users are segmented, reducing noise from outdated or infrequent interactions. The method enhances audience segmentation by dynamically adjusting user categorization based on both the volume and timeliness of their engagement, improving the relevance of targeted media delivery. This approach is particularly useful in digital advertising, content recommendation systems, and user behavior analytics.
4. The method of claim 1 , further comprising: determining a size of an audience of the particular media item based on both passive and active behavioral events, wherein the passive behavioral events are determined using attribution based on contextual markers included in media streams, and active behavioral events are determined based on user activities.
This invention relates to audience measurement for media content, specifically improving the accuracy of determining audience size by combining passive and active behavioral data. The problem addressed is the limitation of traditional audience measurement methods that rely solely on active user interactions (e.g., clicks, likes) or passive tracking (e.g., contextual markers in media streams), which can lead to incomplete or biased audience metrics. The method involves analyzing both passive and active behavioral events to assess the audience size of a particular media item. Passive behavioral events are detected using attribution techniques that leverage contextual markers embedded in media streams, such as timestamps, metadata, or device identifiers. These markers help infer audience engagement without direct user input. Active behavioral events are derived from explicit user actions, such as interactions with the media (e.g., play, pause, share) or related content (e.g., comments, ratings). By integrating these two data sources, the method provides a more comprehensive and accurate measurement of audience size. The passive data compensates for limitations in active tracking, such as users who engage without explicit actions, while active data refines the passive inferences. This hybrid approach enhances the reliability of audience analytics, benefiting media publishers, advertisers, and content creators in optimizing content delivery and monetization strategies.
5. The method of claim 1 , further comprising: inserting the contextual markers into the media stream at a streaming media server.
A method for processing media streams involves inserting contextual markers into a media stream to enhance content analysis, indexing, or retrieval. The contextual markers are data elements that provide metadata or annotations about specific segments of the media stream, such as timestamps, event triggers, or descriptive tags. These markers are inserted at a streaming media server, which distributes the media stream to client devices. The insertion process ensures that the markers are synchronized with the corresponding media content, allowing downstream systems to accurately reference and process the annotated segments. The method may also include generating the contextual markers based on user interactions, automated analysis, or external data sources. By embedding these markers at the server level, the system enables efficient distribution of enriched media content without requiring client-side processing. This approach improves the scalability and reliability of media analysis applications, such as content recommendation, ad insertion, or accessibility features. The method is particularly useful in live or on-demand streaming environments where real-time or near-real-time annotation is required.
6. The method of claim 1 , further comprising: configuring a mobile device to generate calls to the data management platform in response to the mobile device detecting the contextual markers.
A system and method for contextual data management involves a mobile device detecting contextual markers in an environment, such as location-based triggers, time-based triggers, or sensor-based triggers, to identify relevant contextual information. The mobile device then generates calls to a data management platform, which processes and stores the contextual data. The platform may analyze the data to derive insights, such as user behavior patterns or environmental conditions, and may provide recommendations or automated actions based on the analysis. The system ensures that data collection is contextually relevant, reducing unnecessary processing and improving efficiency. The mobile device may also receive and display contextual information from the platform, enhancing user experience by providing timely and relevant data. The method ensures seamless integration between the mobile device and the data management platform, enabling real-time or near-real-time data exchange. This approach improves data accuracy and usability while minimizing computational overhead.
7. The method of claim 1 , further comprising: associating the user with at least one audience segment based on data derived from a station start, data derived during passive station playback, data derived from web page views, and data derived from user interactions.
This invention relates to audience segmentation for personalized content delivery, addressing the challenge of accurately categorizing users based on diverse behavioral data to improve content recommendations. The method involves collecting and analyzing multiple data sources to associate a user with at least one audience segment. These data sources include station start data, passive station playback data, web page view data, and user interaction data. Station start data refers to user-initiated actions that begin content playback, while passive station playback data captures engagement during ongoing playback without explicit user input. Web page view data tracks user browsing activity, and user interaction data records explicit actions like clicks or selections. By integrating these data points, the system dynamically segments users into relevant audience groups, enabling tailored content delivery. The segmentation process leverages behavioral patterns to refine audience targeting, enhancing personalization and user experience. This approach ensures that content recommendations align with user preferences and interests, derived from both active and passive engagement metrics. The method improves upon traditional segmentation techniques by incorporating a broader range of user activity data, leading to more accurate and contextually relevant audience categorization.
8. A system comprising: a server device configured to implement a streaming media server, the streaming media server configured to: integrate contextual markers into spot blocks of a media stream, the spot blocks positioned adjacent to particular media items included in the media stream; transmit the media stream, including the contextual markers, to a content distribution network for delivery to a user client device associated with a user, wherein the contextual marker identifies the particular media items adjacent to the spot blocks into which the contextual markers are integrated; and a data management platform configured to: receive from the user client device, messages including indications that the user client device has played out particular media items identified by the contextual markers; in response to receipt of the messages, record in a memory, an association between the user and the particular media items; identify at least one audience segment associated with the particular media items; generate segment association information, the segment association information associating the user with the at least one audience segment, based, at least in part, on the association between the user and the particular media items and the association between the particular media items and the at least one audience segment; transmit the segment association information to an advertisement server, the advertisement server configured to iteratively refine a targeting specificity of advertisement content provided to the streaming media server by the advertising server; and the streaming media server further configured to generate a media stream including spot blocks, the spot blocks including the advertisement content provided by the advertising server and the contextual markers.
The system involves a streaming media server that integrates contextual markers into spot blocks within a media stream, where these spot blocks are positioned adjacent to specific media items (e.g., songs, videos, or segments). The media stream, including the contextual markers, is transmitted to a content distribution network for delivery to a user's client device. The contextual markers identify the media items adjacent to the spot blocks, enabling tracking of user engagement. A data management platform receives messages from the user's device indicating which media items were played, then records an association between the user and those items. The platform identifies audience segments linked to the media items and generates segment association information, which ties the user to these segments. This information is sent to an advertisement server, which refines the targeting of ads based on user behavior and media preferences. The streaming media server then generates updated media streams with spot blocks containing targeted advertisement content from the ad server, along with contextual markers. This system enhances ad targeting by leveraging user engagement with specific media items, improving the relevance of delivered advertisements.
9. The system of claim 8 , wherein the data management platform is further configured to: increment an instance counter describing a number of instances the user has been associated with the particular media item by a value of one; and associate the user with the audience segment if the instance counter meets a preset threshold value.
A data management platform monitors user interactions with media items, such as videos, articles, or advertisements, to track engagement patterns. The system identifies when a user is associated with a specific media item, such as by viewing, sharing, or interacting with it. Each time the user is associated with the media item, the platform increments an instance counter by one. This counter tracks the cumulative number of times the user has engaged with the media item. If the counter reaches a preset threshold value, the platform categorizes the user into a predefined audience segment. This segmentation allows for targeted content delivery, personalized recommendations, or audience analytics based on repeated engagement with specific media items. The system dynamically updates user associations and audience segments in real-time as new interactions occur, enabling adaptive audience targeting and improved content relevance. The platform may also integrate with external data sources to refine segmentation criteria or validate user behavior patterns.
10. The system of claim 9 , wherein the data management platform is further configured to: determine a recency associated with at least some of the instances the user has been associated with the particular media item; and associate the user with the audience segment if the instance counter meets the preset threshold value, and the recency of the at least some of the instances the user has been associated with the particular media item meets a preset threshold time indicator.
A data management platform for audience segmentation analyzes user interactions with media items to categorize users into specific audience segments. The system tracks instances where a user engages with a particular media item, such as viewing, sharing, or interacting with the content. To refine segmentation accuracy, the platform evaluates both the frequency and recency of these interactions. The system includes an instance counter that tallies the number of times a user has engaged with the media item. If this count meets a predefined threshold, the user is considered for inclusion in the audience segment. Additionally, the platform assesses the recency of these interactions, ensuring that only recent engagements—within a specified time frame—are considered. If both the frequency and recency criteria are satisfied, the user is assigned to the relevant audience segment. This approach enhances the precision of audience targeting by ensuring that segment membership is based on both the volume and timeliness of user interactions with media content.
11. The system of claim 8 , wherein the data management platform is further configured to: determine a size of an audience of the particular media item based on both passive and active behavioral events, wherein the passive behavioral events are determined using attribution based on contextual markers included in media streams, and active behavioral events are determined based on user activities.
A system for audience measurement in media distribution analyzes both passive and active user behaviors to determine the size of an audience for a particular media item. The system includes a data management platform that processes behavioral data from multiple sources. Passive behavioral events are detected using attribution techniques applied to contextual markers embedded in media streams, such as timestamps, metadata, or other identifiers that indicate exposure to the media. Active behavioral events are derived from direct user interactions, such as clicks, views, or engagement metrics. By combining these two types of data, the system provides a comprehensive assessment of audience reach and engagement. The platform may also include components for data collection, processing, and analysis, ensuring accurate and scalable measurement of media consumption across different channels. This approach enhances traditional audience measurement methods by incorporating both inferred and explicit user behaviors, improving the reliability of audience insights for media analytics and advertising optimization.
12. The system of claim 8 , wherein the streaming media server is further configured to: insert the contextual markers into the media stream.
A system for managing streaming media content includes a streaming media server that processes and delivers media streams to client devices. The system addresses the challenge of providing relevant contextual information during media playback, such as advertisements, subtitles, or interactive elements, in a synchronized manner. The streaming media server is configured to receive a media stream and analyze its content to identify key segments or events. Based on this analysis, the server generates contextual markers that represent specific points in the media stream where additional content or actions should be triggered. These markers are then inserted into the media stream at the appropriate locations. The system ensures that the contextual markers are synchronized with the media stream, allowing client devices to display or execute the associated content at the correct times. This approach enhances the user experience by providing timely and contextually relevant information during media playback. The system may also include a client device that receives the media stream with embedded contextual markers and processes them to display or execute the associated content. The server may further communicate with external data sources to retrieve additional information for the contextual markers, ensuring that the content remains up-to-date and relevant.
13. The system of claim 8 , further comprising a client device configured to: generate the indications in response to detecting the contextual markers.
A system for detecting and responding to contextual markers in a computing environment. The system addresses the problem of efficiently identifying and processing contextual markers—such as user actions, environmental conditions, or system states—to trigger automated responses or adjustments. The system includes a processing module that analyzes data streams to detect predefined contextual markers, which may be based on patterns, thresholds, or specific events. Upon detection, the system generates indications, such as alerts, commands, or data signals, to initiate further actions. These indications are then transmitted to a client device, which is configured to generate additional indications in response. The client device may further process the detected markers, execute predefined workflows, or modify its behavior based on the context. The system ensures real-time responsiveness and adaptability to dynamic conditions, improving automation and user interaction in applications like smart environments, industrial control systems, or personalized computing. The client device's role in generating secondary indications enhances flexibility, allowing for localized or device-specific responses tailored to the detected context.
14. The system of claim 8 , wherein the data management platform is further configured to: transmit information indicating an association between the user and the audience segment to an ad server.
A data management platform (DMP) is used to collect, analyze, and manage user data for targeted advertising. A challenge in this domain is efficiently linking user data to specific audience segments and ensuring this information is accessible to ad servers for precise ad targeting. The invention addresses this by enhancing a DMP to transmit association data between users and audience segments to an ad server. The DMP first processes user data to categorize users into predefined audience segments based on attributes such as demographics, behavior, or interests. Once a user is assigned to a segment, the DMP generates and transmits a signal or data packet to an ad server, indicating this association. The ad server then uses this information to deliver personalized ads to the user. This system improves ad targeting accuracy by ensuring the ad server has real-time or up-to-date segment membership data, reducing reliance on outdated or incomplete user profiles. The solution is particularly useful in digital advertising ecosystems where timely and precise audience segmentation is critical for campaign effectiveness. The DMP may also handle data privacy compliance, such as anonymization or consent management, before transmitting segment associations to the ad server.
15. A data management platform comprising: a network interface configured to receive, over time, from a user client device of a user, messages including indications that the user client device has played out particular media items included in a media stream, the messages generated by the user client device in response to encountering contextual markers integrated within spot blocks adjacent to the particular media items in the media stream, the contextual markers including information related to advertisement content included in the spot blocks and to the particular media items; a processor and associated memory coupled to the network interface, the processor and associated memory configured, in response to receipt of the messages, to: record in a memory an association between the user and the particular media items; identify at least one audience segment associated with the particular media items; increment an instance counter describing a number of instances the user has been associated with the particular media item by a value of one; and generate segment association information, the segment association information associating the user with the at least one audience segment based, at least in part, on the association between the user and the particular media item and the association between the particular media item and the at least one audience segment; and transmitting the segment association information from the data management platform to an advertisement server, the advertisement server configured to iteratively refine a targeting specificity of advertisement content provided to a streaming server by the advertising server based on the segment association information.
The data management platform is designed for audience segmentation and targeted advertising in media streaming systems. The system addresses the challenge of dynamically refining advertisement targeting based on user engagement with media content. The platform receives messages from user devices indicating playback of specific media items within a stream. These messages are triggered by contextual markers embedded in spot blocks adjacent to the media items, which contain metadata about both the media content and associated advertisements. Upon receiving these messages, the platform records the user's association with the media items, identifies relevant audience segments linked to those items, and increments a counter tracking the user's exposure to the content. The system then generates segment association information, linking the user to the identified audience segments based on their interaction with the media items. This information is transmitted to an advertisement server, which uses it to iteratively refine the specificity of advertisements delivered to a streaming server. The platform enables precise audience segmentation and dynamic ad targeting by leveraging contextual metadata and user engagement data.
16. The data management platform of claim 15 , wherein the processor and associated memory are further configured to: associate the user with the audience segment if the instance counter meets a preset threshold value.
A data management platform is designed to analyze user behavior and segment users into specific audience groups based on their interactions with digital content. The platform addresses the challenge of efficiently categorizing users to enable targeted content delivery, advertising, or personalized experiences. The system includes a processor and memory that track user interactions, such as clicks, views, or other engagement metrics, and increment an instance counter for each interaction. When the counter reaches a preset threshold, the user is automatically assigned to a predefined audience segment. This segmentation allows for more precise targeting, improving the relevance of content or advertisements delivered to the user. The platform may also include additional features, such as real-time tracking, dynamic threshold adjustments, and integration with external data sources to refine audience segmentation further. By automating the segmentation process, the platform enhances efficiency and accuracy in user targeting, benefiting digital marketers, content providers, and other stakeholders relying on audience analytics.
17. The data management platform of claim 15 , wherein the processor and associated memory are further configured to: determine a recency associated with at least some of the instances the user has been associated with the particular media item; and associate the user with the audience segment if the instance counter meets a preset threshold value, and the recency of the at least some of the instances the user has been associated with the particular media item meets a preset threshold time indicator.
A data management platform analyzes user interactions with media items to segment users into targeted audience groups. The system tracks instances where a user engages with a specific media item, such as viewing, sharing, or purchasing it, and evaluates both the frequency and recency of these interactions. The platform includes a processor and memory that determine how recently a user has interacted with the media item and whether the total number of interactions meets a predefined threshold. If both the frequency and recency criteria are satisfied, the user is assigned to a specific audience segment for targeted marketing or content delivery. This approach ensures that audience segmentation is based on both the volume and timeliness of user engagement, improving the relevance of targeted communications. The system may also incorporate additional user behavior data to refine segmentation further.
18. The data management platform of claim 15 , wherein the processor and associated memory are further configured to: determine a size of an audience of the particular media item based on both passive and active behavioral events, wherein the passive behavioral events are determined using attribution based on contextual markers included in media streams, and active behavioral events are determined based on user activities.
This invention relates to a data management platform for analyzing media consumption behavior. The platform addresses the challenge of accurately measuring audience engagement with media content by integrating both passive and active behavioral data. Passive behavioral events are detected through contextual markers embedded in media streams, allowing the system to infer user exposure without direct interaction. Active behavioral events are captured based on explicit user activities, such as clicks, searches, or direct engagement with the media. The platform combines these data sources to determine the size of an audience for a particular media item, providing a more comprehensive understanding of user behavior. The system processes media streams to identify contextual markers, which may include metadata, timestamps, or other embedded signals that indicate when and how a user was exposed to the content. User activities are tracked through interaction logs, session data, or other direct engagement metrics. By analyzing both passive and active signals, the platform generates a more accurate audience measurement, enabling better content targeting, performance analytics, and user experience optimization. The invention enhances traditional audience measurement techniques by incorporating contextual and behavioral data, reducing reliance on self-reported or incomplete interaction data.
19. The data management platform of claim 15 , wherein the indications include notifications generated by and received from a mobile device in response to the mobile device detecting the contextual markers.
A data management platform is designed to process and analyze contextual markers, which are indicators of specific conditions or events in a physical or digital environment. These markers can include sensor data, location information, or other contextual signals that trigger automated actions or notifications. The platform receives indications, such as alerts or status updates, from mobile devices that detect these contextual markers. When a mobile device identifies a relevant marker, it generates and transmits a notification to the platform, which then processes the information to facilitate decision-making, automation, or user interaction. The system may integrate with various sensors, applications, or external data sources to enhance contextual awareness and responsiveness. This approach enables dynamic adaptation to changing conditions, improving efficiency in applications such as smart environments, asset tracking, or personalized services. The platform ensures timely and accurate handling of contextual data to support real-time operations and user engagement.
20. The data management platform of claim 15 , wherein the processor and associated memory are further configured to: associate the user with at least one audience segment based on data derived from a station start, data derived during passive station playback, data derived from web page views, and data derived from user interactions.
This invention relates to a data management platform designed to enhance user profiling and audience segmentation by analyzing diverse user activity data. The platform collects and processes multiple types of user data to create detailed audience segments. Specifically, it associates users with segments based on data derived from station starts (e.g., when a user initiates media playback), passive station playback (e.g., background listening or viewing), web page views (e.g., browsing history), and user interactions (e.g., clicks, searches, or other engagement actions). The platform uses this aggregated data to refine audience targeting, enabling more personalized content delivery or advertising. The underlying system includes a processor and memory configured to perform these operations, ensuring real-time or near-real-time analysis of user behavior across different digital touchpoints. By integrating these varied data sources, the platform provides a comprehensive view of user preferences and habits, improving the accuracy of audience segmentation compared to systems relying on limited or siloed data types. This approach supports applications in digital advertising, content recommendation, and user experience optimization.
Unknown
December 1, 2020
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.